Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915232911196160 |
|---|---|
| author | Werenski, Matthew Mallery, Brendan Aeron, Shuchin Murphy, James M. |
| author_facet | Werenski, Matthew Mallery, Brendan Aeron, Shuchin Murphy, James M. |
| contents | We propose the linear barycentric coding model (LBCM) which utilizes the linear optimal transport (LOT) metric for analysis and synthesis of probability measures. We provide a closed-form solution to the variational problem characterizing the probability measures in the LBCM and establish equivalence of the LBCM to the set of 2-Wasserstein barycenters in the special case of compatible measures. Computational methods for synthesizing and analyzing measures in the LBCM are developed with finite sample guarantees. One of our main theoretical contributions is to identify an LBCM, expressed in terms of a simple family, which is sufficient to express all probability measures on the closed unit interval. We show that a natural analogous construction of an LBCM in 2 dimensions fails, and we leave it as an open problem to identify the proper extension in more than 1 dimension. We conclude by demonstrating the utility of LBCM for covariance estimation and data imputation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23602 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications Werenski, Matthew Mallery, Brendan Aeron, Shuchin Murphy, James M. Machine Learning We propose the linear barycentric coding model (LBCM) which utilizes the linear optimal transport (LOT) metric for analysis and synthesis of probability measures. We provide a closed-form solution to the variational problem characterizing the probability measures in the LBCM and establish equivalence of the LBCM to the set of 2-Wasserstein barycenters in the special case of compatible measures. Computational methods for synthesizing and analyzing measures in the LBCM are developed with finite sample guarantees. One of our main theoretical contributions is to identify an LBCM, expressed in terms of a simple family, which is sufficient to express all probability measures on the closed unit interval. We show that a natural analogous construction of an LBCM in 2 dimensions fails, and we leave it as an open problem to identify the proper extension in more than 1 dimension. We conclude by demonstrating the utility of LBCM for covariance estimation and data imputation. |
| title | Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.23602 |